Abstract: The present invention discloses a method for constructing a surface stress distribution cloud map based on critical refraction longitudinal wave detection. The method comprises: firstly, meshing a surface of a detected article; secondly, The mean transverse stress on different grid lines and the mean longitudinal stress on different grid lines were obtained by the critical refraction longitudinal wave detection method; next, calculating the equivalent stress of each mesh node according to the mean transverse stress on different mesh transverse lines and the mean longitudinal stress on different mesh longitudinal lines on the surface of the detected article; and finally, drawing a stress distribution cloud map of the surface of the detected article according to the equivalent stress. The present invention can obtain the stress situations at different points on the surface of the detected article.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: A camera optical lens is provided, including from an object side to an image side: a first lens having positive refractive power; a second lens having positive refractive power; a third lens having positive refractive power; a fourth lens having negative refractive power; a fifth lens having negative refractive power; a sixth lens having positive refractive power; and a seventh lens having negative refractive power. The camera optical lens satisfies following conditions: 1.50?f2/f?5 0.00; ?9.50?(R9+R10)/(R9?R10)??1.20; ?2.00?f7/f??0.60, where f denotes focal length of the camera optical lens; f2 denotes focal length of the second lens; f7 denotes focal length of the seventh lens; R9 denotes central curvature radius of object side surface of the fifth lens; and R10 denotes central curvature radius of image side surface of the fifth lens. The above camera optical lens may meet design requirements for large aperture, wide angle and ultra-thinness, while maintaining good imaging quality.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Abstract: Provided is a camera optical lens including first to fourth lenses. The camera optical lens satisfies: 0.10?R1/R2?0.20; 1.10?R3/R4?1.50; 5.50?R5/R6?6.50; and ?6.50?f2/f??4.50, where f denotes a focal length of the camera optical lens; f2 denotes a focal length of the second lens; R1 denotes a curvature radius of an object side surface of the first lens; R2 denotes a curvature radius of an image side surface of the first lens; R3 denotes a curvature radius of an object side surface of the second lens; R4 denotes a curvature radius of an image side surface of the second lens; R5 denotes a curvature radius of an object side surface of the third lens; and R6 denotes a curvature radius of an image side surface of the third lens. The camera optical lens has good optical performance while satisfying design requirements for ultra-thin, wide-angle lenses having large apertures.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified digital image from extracted spatial and global codes. For example, the disclosed systems can utilize a global and spatial autoencoder to extract spatial codes and global codes from digital images. The disclosed systems can further utilize the global and spatial autoencoder to generate a modified digital image by combining extracted spatial and global codes in various ways for various applications such as style swapping, style blending, and attribute editing.

Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Abstract: The present disclosure relates to the field of optical lenses and provides a camera optical lens. The camera optical lens includes, from an object side to an image side: a first lens; a second lens; a third lens; a fourth lens; a fifth lens; a sixth lens; a seventh lens; and an eighth lens. The camera optical lens satisfies following conditions: 3.50?f1/f?6.50; f2?0; and 1.55?n7?1.70, where f denotes a focal length of the camera optical lens; f1 denotes a focal length of the first lens; f2 denotes a focal length of the second lens; and n7 denotes a refractive index of the seventh lens. The present disclosure can achieve ultra-thin, wide-angle lenses having a big aperture.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize a contrastive perceptual loss to modify neural networks for generating synthetic digital content items. For example, the disclosed systems generate a synthetic digital content item based on a guide input to a generative neural network. The disclosed systems utilize an encoder neural network to generate encoded representations of the synthetic digital content item and a corresponding ground-truth digital content item. Additionally, the disclosed systems sample patches from the encoded representations of the encoded digital content items and then determine a contrastive loss based on the perceptual distances between the patches in the encoded representations. Furthermore, the disclosed systems jointly update the parameters of the generative neural network and the encoder neural network utilizing the contrastive loss.

Abstract: The present invention relates to the technical field of optical lens and discloses a camera optical lens satisfying following conditions: ?0.50?f1/f2??0.35; 5.00?f3/f?14.00; ?3.10?(f2+f5)/f??2.40; 3.00?(R3+R4)/(R3?R4)?4.00; 1.20?(R7+R8)/(R7?R8)?1.30; 0.25?(R9+R10)/(R9?R10)?0.65; where f denotes a focal length of the camera optical lens; f1, f2, f3 and f5 respectively denote a focal length of the first, second, third and fifth lenses; R3, R7 and R9 respectively denote a curvature radius of an object-side surface of the second, fourth and fifth lenses; R4, R8 and R10 respectively denote a curvature radius of an image-side surface of the second, fourth and fifth lenses.

Abstract: The present invention relates to the technical field of optical lens and discloses a camera optical lens satisfying following conditions: ?3.50?f2/f??1.50, 6.50?d1/d2?13.50, ?0.20?(R9+R10)/(R9?R10)??0.05, and 3.00?R6/f?10.00; where f denotes a focal length of the camera optical lens, f2 a focal length of the second lens, d1 an on-axis thickness of the first lens, d2 an on-axis distance from an image-side surface of the first lens to an object-side surface of the second lens, R6 a curvature radius of an image-side surface of the third lens, R9 a curvature radius of an object-side surface of the fifth lens, and R10 a curvature radius of an image-side surface of the fifth lens. The camera optical lens in the present disclosure satisfies a design requirement of large aperture, ultra-thinness and wide angle while having good optical functions.

Abstract: A target image is projected into a latent space of generative model by determining a latent vector by applying a gradient-free technique and a class vector by applying a gradient-based technique. An image is generated from the latent and class vectors, and a loss function is used to determine a loss between the target image and the generated image. This determining of the latent vector and the class vector, generating an image, and using the loss function is repeated until a loss condition is satisfied. In response to the loss condition being satisfied, the latent and class vectors that resulted in the loss condition being satisfied are identified as the final latent and class vectors, respectively. The final latent and class vectors are provided to the generative model and multiple weights of the generative model are adjusted to fine-tune the generative model.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating modified digital images utilizing a novel swapping autoencoder that incorporates scene layout. In particular, the disclosed systems can receive a scene layout map that indicates or defines locations for displaying specific digital content within a digital image. In addition, the disclosed systems can utilize the scene layout map to guide combining portions of digital image latent code to generate a modified digital image with a particular textural appearance and a particular geometric structure defined by the scene layout map. Additionally, the disclosed systems can utilize a scene layout map that defines a portion of a digital image to modify by, for instance, adding new digital content to the digital image, and can generate a modified digital image depicting the new digital content.

Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize a contrastive perceptual loss to modify neural networks for generating synthetic digital content items. For example, the disclosed systems generate a synthetic digital content item based on a guide input to a generative neural network. The disclosed systems utilize an encoder neural network to generate encoded representations of the synthetic digital content item and a corresponding ground-truth digital content item. Additionally, the disclosed systems sample patches from the encoded representations of the encoded digital content items and then determine a contrastive loss based on the perceptual distances between the patches in the encoded representations. Furthermore, the disclosed systems jointly update the parameters of the generative neural network and the encoder neural network utilizing the contrastive loss.

Abstract: A camera optical lens includes, from an object side to an image side: a first lens, a second lens, a third lens, a fourth lens, a fifth lens and a sixth lens. The camera optical lens satisfies conditions of ?4.00?f1/f??2.20, 1.50?f2/f?3.50, 3.00?R7/R8?8.00, 1.50?(R9+R10)/(R9?R10)?8.00, and 1.50?d8/d10?5.00. Here f denotes a focal length of the camera optical lens, f1 denotes a focal length of the first lens, f2 denotes a focal length of the second lens, R7 denotes a curvature radius of an object-side surface of the fourth lens, R8 denotes a curvature radius of an image-side surface of the fourth lens, R9 denotes an curvature radius of an object-side surface of the fifth lens, R10 denotes a curvature radius of an image-side surface of the fifth lens. The camera optical lens of the present disclosure has excellent optical performances, and meanwhile can meet design requirements of a wide angle and ultra-thin.

Abstract: The present disclosure provides a camera optical lens including, from an object side to an image side in sequence: a first lens, a second, a third lens, a fourth lens, a fifth lens, a sixth lens, a seventh lens, and an eighth lens; the first lens has a positive refractive power, and the camera optical lens satisfies conditions of: 0.95?f/TTL; 2.00?f2/f?5.00; and ?20.00?(R13+R14)/(R13?R14)??3.00. The camera optical lens can achieve good optical performance while meeting the design requirements for long focal length and ultra-thinness.

Abstract: A camera optical lens is provided. The camera optical lens includes, from an object side to an image side, a first lens having positive refractive power, a second lens having positive refractive power, a third lens having negative refractive power, a fourth lens having positive refractive power, a fifth lens having negative refractive power, a sixth lens having negative refractive power, a seventh lens having positive refractive power, an eighth lens, and a ninth lens having negative refractive power. The camera optical lens satisfies: 1.90?f1/f?3.50; and 4.00?d9/d10?15.00, where f denotes a focal length of the camera optical lens, f1 denotes a focal length of the first lens, d9 denotes an on-axis thickness of the fifth lens, and d10 denotes an on-axis distance from an image side surface of the fifth lens to an object side surface of the sixth lens. The camera optical lens can facilitate achieving ultra-thin lenses.